Merge branch '40GbE' of git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/net-queue

Jeff Kirsher says:

====================
Intel Wired LAN Driver Fixes 2017-11-21

This series contains fixes for igb/vf, ixgbe/vf, i40e/vf and fm10k.

Jake fixes a regression issue with older firmware, where we were using
the NVM lock to synchronize NVM reads for all devices and firmware
versions, yet this caused issues with older firmware prior to version
1.5.  Fixed this by only grabbing the lock for newer devices and firmware
version 1.5 or newer.

Zijie Pan fixes the calculation of the i40e VF MAC addresses, where it was
possible to increment to the next MAC entry without calling
i40e_add_mac_filter().

Amritha removes the upper limit of 64 queues on a channel VSI since the
upper bound is determined by the VSI's num_queue_pairs.

Filip fixes an issue during FLR resets, where should have been checking
for upcoming core reset and if so, just return with I40E_ERR_NOT_READY.

Alan fixes the notifying clients of l2 parameters by copying the
parameters to the client instance struct and re-organizes the priority
in which the client tasks fire so that if the flag for notifying l2
params is set, it will trigger before the client open task.  Also fixed
the promiscuous settings after reset for all the VSI's.

Brian King from IBM fixes an issue seen on Power systems which would
result in skb list corruption and eventual kernel oops.  Brian
provides the same fix for nearly all our drivers, to replace the
read_barrier_depends with smp_rmb() to ensure loads are ordered with
respect to the load of tx_buffer->next_to_watch.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/fm10k/fm10k_main.c

@@ -1231,7 +1231,7 @@ static bool fm10k_clean_tx_irq(struct fm10k_q_vector *q_vector,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->flags & FM10K_TXD_FLAG_DONE))

drivers/net/ethernet/intel/i40e/i40e.h

@@ -90,7 +90,6 @@
 #define I40E_AQ_LEN			256
 #define I40E_AQ_WORK_LIMIT		66 /* max number of VFs + a little */
 #define I40E_MAX_USER_PRIORITY		8
-#define I40E_MAX_QUEUES_PER_CH		64
 #define I40E_DEFAULT_TRAFFIC_CLASS	BIT(0)
 #define I40E_DEFAULT_MSG_ENABLE		4
 #define I40E_QUEUE_WAIT_RETRY_LIMIT	10

drivers/net/ethernet/intel/i40e/i40e_adminq.c

@@ -613,6 +613,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw)
 		hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE;
 	}
 
+	/* Newer versions of firmware require lock when reading the NVM */
+	if (hw->aq.api_maj_ver > 1 ||
+	    (hw->aq.api_maj_ver == 1 &&
+	     hw->aq.api_min_ver >= 5))
+		hw->flags |= I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK;
+
 	/* The ability to RX (not drop) 802.1ad frames was added in API 1.7 */
 	if (hw->aq.api_maj_ver > 1 ||
 	    (hw->aq.api_maj_ver == 1 &&

drivers/net/ethernet/intel/i40e/i40e_common.c

@@ -948,7 +948,8 @@ i40e_status i40e_init_shared_code(struct i40e_hw *hw)
 		hw->pf_id = (u8)(func_rid & 0x7);
 
 	if (hw->mac.type == I40E_MAC_X722)
-		hw->flags |= I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE;
+		hw->flags |= I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE |
+			     I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK;
 
 	status = i40e_init_nvm(hw);
 	return status;
@@ -1268,6 +1269,7 @@ i40e_status i40e_pf_reset(struct i40e_hw *hw)
 	 * we don't need to do the PF Reset
 	 */
 	if (!cnt) {
+		u32 reg2 = 0;
 		if (hw->revision_id == 0)
 			cnt = I40E_PF_RESET_WAIT_COUNT_A0;
 		else
@@ -1279,6 +1281,12 @@ i40e_status i40e_pf_reset(struct i40e_hw *hw)
 			reg = rd32(hw, I40E_PFGEN_CTRL);
 			if (!(reg & I40E_PFGEN_CTRL_PFSWR_MASK))
 				break;
+			reg2 = rd32(hw, I40E_GLGEN_RSTAT);
+			if (reg2 & I40E_GLGEN_RSTAT_DEVSTATE_MASK) {
+				hw_dbg(hw, "Core reset upcoming. Skipping PF reset request.\n");
+				hw_dbg(hw, "I40E_GLGEN_RSTAT = 0x%x\n", reg2);
+				return I40E_ERR_NOT_READY;
+			}
 			usleep_range(1000, 2000);
 		}
 		if (reg & I40E_PFGEN_CTRL_PFSWR_MASK) {

drivers/net/ethernet/intel/i40e/i40e_main.c

@@ -2166,6 +2166,73 @@ i40e_aqc_broadcast_filter(struct i40e_vsi *vsi, const char *vsi_name,
 	return aq_ret;
 }
 
+/**
+ * i40e_set_promiscuous - set promiscuous mode
+ * @pf: board private structure
+ * @promisc: promisc on or off
+ *
+ * There are different ways of setting promiscuous mode on a PF depending on
+ * what state/environment we're in.  This identifies and sets it appropriately.
+ * Returns 0 on success.
+ **/
+static int i40e_set_promiscuous(struct i40e_pf *pf, bool promisc)
+{
+	struct i40e_vsi *vsi = pf->vsi[pf->lan_vsi];
+	struct i40e_hw *hw = &pf->hw;
+	i40e_status aq_ret;
+
+	if (vsi->type == I40E_VSI_MAIN &&
+	    pf->lan_veb != I40E_NO_VEB &&
+	    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
+		/* set defport ON for Main VSI instead of true promisc
+		 * this way we will get all unicast/multicast and VLAN
+		 * promisc behavior but will not get VF or VMDq traffic
+		 * replicated on the Main VSI.
+		 */
+		if (promisc)
+			aq_ret = i40e_aq_set_default_vsi(hw,
+							 vsi->seid,
+							 NULL);
+		else
+			aq_ret = i40e_aq_clear_default_vsi(hw,
+							   vsi->seid,
+							   NULL);
+		if (aq_ret) {
+			dev_info(&pf->pdev->dev,
+				 "Set default VSI failed, err %s, aq_err %s\n",
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		}
+	} else {
+		aq_ret = i40e_aq_set_vsi_unicast_promiscuous(
+						  hw,
+						  vsi->seid,
+						  promisc, NULL,
+						  true);
+		if (aq_ret) {
+			dev_info(&pf->pdev->dev,
+				 "set unicast promisc failed, err %s, aq_err %s\n",
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		}
+		aq_ret = i40e_aq_set_vsi_multicast_promiscuous(
+						  hw,
+						  vsi->seid,
+						  promisc, NULL);
+		if (aq_ret) {
+			dev_info(&pf->pdev->dev,
+				 "set multicast promisc failed, err %s, aq_err %s\n",
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
+		}
+	}
+
+	if (!aq_ret)
+		pf->cur_promisc = promisc;
+
+	return aq_ret;
+}
+
 /**
  * i40e_sync_vsi_filters - Update the VSI filter list to the HW
  * @vsi: ptr to the VSI
@@ -2467,81 +2534,16 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi)
 		cur_promisc = (!!(vsi->current_netdev_flags & IFF_PROMISC) ||
 			       test_bit(__I40E_VSI_OVERFLOW_PROMISC,
 					vsi->state));
-		if ((vsi->type == I40E_VSI_MAIN) &&
-		    (pf->lan_veb != I40E_NO_VEB) &&
-		    !(pf->flags & I40E_FLAG_MFP_ENABLED)) {
-			/* set defport ON for Main VSI instead of true promisc
-			 * this way we will get all unicast/multicast and VLAN
-			 * promisc behavior but will not get VF or VMDq traffic
-			 * replicated on the Main VSI.
-			 */
-			if (pf->cur_promisc != cur_promisc) {
-				pf->cur_promisc = cur_promisc;
-				if (cur_promisc)
-					aq_ret =
-					      i40e_aq_set_default_vsi(hw,
-								      vsi->seid,
-								      NULL);
-				else
-					aq_ret =
-					    i40e_aq_clear_default_vsi(hw,
-								      vsi->seid,
-								      NULL);
-				if (aq_ret) {
-					retval = i40e_aq_rc_to_posix(aq_ret,
-							hw->aq.asq_last_status);
-					dev_info(&pf->pdev->dev,
-						 "Set default VSI failed on %s, err %s, aq_err %s\n",
-						 vsi_name,
-						 i40e_stat_str(hw, aq_ret),
-						 i40e_aq_str(hw,
-						     hw->aq.asq_last_status));
-				}
-			}
-		} else {
-			aq_ret = i40e_aq_set_vsi_unicast_promiscuous(
-							  hw,
-							  vsi->seid,
-							  cur_promisc, NULL,
-							  true);
-			if (aq_ret) {
-				retval =
-				i40e_aq_rc_to_posix(aq_ret,
-						    hw->aq.asq_last_status);
-				dev_info(&pf->pdev->dev,
-					 "set unicast promisc failed on %s, err %s, aq_err %s\n",
-					 vsi_name,
-					 i40e_stat_str(hw, aq_ret),
-					 i40e_aq_str(hw,
-						     hw->aq.asq_last_status));
-			}
-			aq_ret = i40e_aq_set_vsi_multicast_promiscuous(
-							  hw,
-							  vsi->seid,
-							  cur_promisc, NULL);
-			if (aq_ret) {
-				retval =
-				i40e_aq_rc_to_posix(aq_ret,
-						    hw->aq.asq_last_status);
-				dev_info(&pf->pdev->dev,
-					 "set multicast promisc failed on %s, err %s, aq_err %s\n",
-					 vsi_name,
-					 i40e_stat_str(hw, aq_ret),
-					 i40e_aq_str(hw,
-						     hw->aq.asq_last_status));
-			}
-		}
-		aq_ret = i40e_aq_set_vsi_broadcast(&vsi->back->hw,
-						   vsi->seid,
-						   cur_promisc, NULL);
+		aq_ret = i40e_set_promiscuous(pf, cur_promisc);
 		if (aq_ret) {
 			retval = i40e_aq_rc_to_posix(aq_ret,
-						     pf->hw.aq.asq_last_status);
+						     hw->aq.asq_last_status);
 			dev_info(&pf->pdev->dev,
-				 "set brdcast promisc failed, err %s, aq_err %s\n",
-					 i40e_stat_str(hw, aq_ret),
-					 i40e_aq_str(hw,
-						     hw->aq.asq_last_status));
+				 "Setting promiscuous %s failed on %s, err %s aq_err %s\n",
+				 cur_promisc ? "on" : "off",
+				 vsi_name,
+				 i40e_stat_str(hw, aq_ret),
+				 i40e_aq_str(hw, hw->aq.asq_last_status));
 		}
 	}
 out:
@@ -3964,7 +3966,7 @@ static bool i40e_clean_fdir_tx_irq(struct i40e_ring *tx_ring, int budget)
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if the descriptor isn't done, no work yet to do */
 		if (!(eop_desc->cmd_type_offset_bsz &
@@ -5629,14 +5631,6 @@ static int i40e_validate_num_queues(struct i40e_pf *pf, int num_queues,
 		return -EINVAL;
 
 	*reconfig_rss = false;
-
-	if (num_queues > I40E_MAX_QUEUES_PER_CH) {
-		dev_err(&pf->pdev->dev,
-			"Failed to create VMDq VSI. User requested num_queues (%d) > I40E_MAX_QUEUES_PER_VSI (%u)\n",
-			num_queues, I40E_MAX_QUEUES_PER_CH);
-		return -EINVAL;
-	}
-
 	if (vsi->current_rss_size) {
 		if (num_queues > vsi->current_rss_size) {
 			dev_dbg(&pf->pdev->dev,
@@ -9429,6 +9423,15 @@ static void i40e_rebuild(struct i40e_pf *pf, bool reinit, bool lock_acquired)
 	if (!lock_acquired)
 		rtnl_unlock();
 
+	/* Restore promiscuous settings */
+	ret = i40e_set_promiscuous(pf, pf->cur_promisc);
+	if (ret)
+		dev_warn(&pf->pdev->dev,
+			 "Failed to restore promiscuous setting: %s, err %s aq_err %s\n",
+			 pf->cur_promisc ? "on" : "off",
+			 i40e_stat_str(&pf->hw, ret),
+			 i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status));
+
 	i40e_reset_all_vfs(pf, true);
 
 	/* tell the firmware that we're starting */

drivers/net/ethernet/intel/i40e/i40e_nvm.c

@@ -328,15 +328,17 @@ static i40e_status __i40e_read_nvm_word(struct i40e_hw *hw,
 i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset,
 			       u16 *data)
 {
-	i40e_status ret_code;
+	i40e_status ret_code = 0;
 
-	ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
+	if (hw->flags & I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK)
+		ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ);
 	if (ret_code)
 		return ret_code;
 
 	ret_code = __i40e_read_nvm_word(hw, offset, data);
 
-	i40e_release_nvm(hw);
+	if (hw->flags & I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK)
+		i40e_release_nvm(hw);
 
 	return ret_code;
 }

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -759,7 +759,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* we have caught up to head, no work left to do */

drivers/net/ethernet/intel/i40e/i40e_type.h

@@ -629,6 +629,7 @@ struct i40e_hw {
 #define I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE BIT_ULL(0)
 #define I40E_HW_FLAG_802_1AD_CAPABLE        BIT_ULL(1)
 #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE  BIT_ULL(2)
+#define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3)
 	u64 flags;
 
 	/* Used in set switch config AQ command */

drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c

@@ -2218,18 +2218,19 @@ static int i40e_vc_add_mac_addr_msg(struct i40e_vf *vf, u8 *msg, u16 msglen)
 		struct i40e_mac_filter *f;
 
 		f = i40e_find_mac(vsi, al->list[i].addr);
-		if (!f)
+		if (!f) {
 			f = i40e_add_mac_filter(vsi, al->list[i].addr);
 
-		if (!f) {
-			dev_err(&pf->pdev->dev,
-				"Unable to add MAC filter %pM for VF %d\n",
-				 al->list[i].addr, vf->vf_id);
-			ret = I40E_ERR_PARAM;
-			spin_unlock_bh(&vsi->mac_filter_hash_lock);
-			goto error_param;
-		} else {
-			vf->num_mac++;
+			if (!f) {
+				dev_err(&pf->pdev->dev,
+					"Unable to add MAC filter %pM for VF %d\n",
+					al->list[i].addr, vf->vf_id);
+				ret = I40E_ERR_PARAM;
+				spin_unlock_bh(&vsi->mac_filter_hash_lock);
+				goto error_param;
+			} else {
+				vf->num_mac++;
+			}
 		}
 	}
 	spin_unlock_bh(&vsi->mac_filter_hash_lock);

drivers/net/ethernet/intel/i40evf/i40e_txrx.c

@@ -179,7 +179,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		i40e_trace(clean_tx_irq, tx_ring, tx_desc, tx_buf);
 		/* if the descriptor isn't done, no work yet to do */

drivers/net/ethernet/intel/i40evf/i40evf_client.c

@@ -25,6 +25,26 @@ static struct i40e_ops i40evf_lan_ops = {
 	.setup_qvlist = i40evf_client_setup_qvlist,
 };
 
+/**
+ * i40evf_client_get_params - retrieve relevant client parameters
+ * @vsi: VSI with parameters
+ * @params: client param struct
+ **/
+static
+void i40evf_client_get_params(struct i40e_vsi *vsi, struct i40e_params *params)
+{
+	int i;
+
+	memset(params, 0, sizeof(struct i40e_params));
+	params->mtu = vsi->netdev->mtu;
+	params->link_up = vsi->back->link_up;
+
+	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
+		params->qos.prio_qos[i].tc = 0;
+		params->qos.prio_qos[i].qs_handle = vsi->qs_handle;
+	}
+}
+
 /**
  * i40evf_notify_client_message - call the client message receive callback
  * @vsi: the VSI associated with this client
@@ -66,10 +86,6 @@ void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
 		return;
 
 	cinst = vsi->back->cinst;
-	memset(&params, 0, sizeof(params));
-	params.mtu = vsi->netdev->mtu;
-	params.link_up = vsi->back->link_up;
-	params.qos.prio_qos[0].qs_handle = vsi->qs_handle;
 
 	if (!cinst || !cinst->client || !cinst->client->ops ||
 	    !cinst->client->ops->l2_param_change) {
@@ -77,6 +93,8 @@ void i40evf_notify_client_l2_params(struct i40e_vsi *vsi)
 			"Cannot locate client instance l2_param_change function\n");
 		return;
 	}
+	i40evf_client_get_params(vsi, &params);
+	cinst->lan_info.params = params;
 	cinst->client->ops->l2_param_change(&cinst->lan_info, cinst->client,
 					    &params);
 }
@@ -166,9 +184,9 @@ static struct i40e_client_instance *
 i40evf_client_add_instance(struct i40evf_adapter *adapter)
 {
 	struct i40e_client_instance *cinst = NULL;
-	struct netdev_hw_addr *mac = NULL;
 	struct i40e_vsi *vsi = &adapter->vsi;
-	int i;
+	struct netdev_hw_addr *mac = NULL;
+	struct i40e_params params;
 
 	if (!vf_registered_client)
 		goto out;
@@ -192,18 +210,14 @@ i40evf_client_add_instance(struct i40evf_adapter *adapter)
 	cinst->lan_info.version.major = I40EVF_CLIENT_VERSION_MAJOR;
 	cinst->lan_info.version.minor = I40EVF_CLIENT_VERSION_MINOR;
 	cinst->lan_info.version.build = I40EVF_CLIENT_VERSION_BUILD;
+	i40evf_client_get_params(vsi, &params);
+	cinst->lan_info.params = params;
 	set_bit(__I40E_CLIENT_INSTANCE_NONE, &cinst->state);
 
 	cinst->lan_info.msix_count = adapter->num_iwarp_msix;
 	cinst->lan_info.msix_entries =
 			&adapter->msix_entries[adapter->iwarp_base_vector];
 
-	for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) {
-		cinst->lan_info.params.qos.prio_qos[i].tc = 0;
-		cinst->lan_info.params.qos.prio_qos[i].qs_handle =
-								vsi->qs_handle;
-	}
-
 	mac = list_first_entry(&cinst->lan_info.netdev->dev_addrs.list,
 			       struct netdev_hw_addr, list);
 	if (mac)

drivers/net/ethernet/intel/i40evf/i40evf_main.c

@@ -2110,6 +2110,11 @@ static void i40evf_client_task(struct work_struct *work)
 		adapter->flags &= ~I40EVF_FLAG_SERVICE_CLIENT_REQUESTED;
 		goto out;
 	}
+	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
+		i40evf_notify_client_l2_params(&adapter->vsi);
+		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
+		goto out;
+	}
 	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_CLOSE) {
 		i40evf_notify_client_close(&adapter->vsi, false);
 		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_CLOSE;
@@ -2118,11 +2123,6 @@ static void i40evf_client_task(struct work_struct *work)
 	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_OPEN) {
 		i40evf_notify_client_open(&adapter->vsi);
 		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_OPEN;
-		goto out;
-	}
-	if (adapter->flags & I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS) {
-		i40evf_notify_client_l2_params(&adapter->vsi);
-		adapter->flags &= ~I40EVF_FLAG_CLIENT_NEEDS_L2_PARAMS;
 	}
 out:
 	clear_bit(__I40EVF_IN_CLIENT_TASK, &adapter->crit_section);

drivers/net/ethernet/intel/igb/igb_main.c

@@ -7317,7 +7317,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector, int napi_budget)
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)))

drivers/net/ethernet/intel/igbvf/netdev.c

@@ -810,7 +810,7 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring)
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)))

drivers/net/ethernet/intel/ixgbe/ixgbe_main.c

@@ -1192,7 +1192,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))

drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c

@@ -326,7 +326,7 @@ static bool ixgbevf_clean_tx_irq(struct ixgbevf_q_vector *q_vector,
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		read_barrier_depends();
+		smp_rmb();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(IXGBE_TXD_STAT_DD)))